OpenAI · LLM API pricing

gpt-oss-120b API pricing: cheapest provider

19 providers sell gpt-oss-120b. W&B Inference (CoreWeave) is cheapest; the most expensive charges 6.9× as much for the same model.

Cheapest$0.065per 1M · W&B Inference (CoreWeave)
Input · output$0.03 / $0.17per 1M tokens
Price gap6.9×across 19 providers
Accuracy75.8%GPQA · high reasoning
Context131Kmax tokens

$0.065 W&B Inference (CoreWeave)6.9× spread$0.45 Cloudflare Workers AI

Compare all 19 providers ⇄ Compare with another model

Already paying for gpt-oss-120b? Check if you overpay →

Standard list prices in USD from each provider's pricing page · last price change Nov 2, 2026 · How we collect and rank prices

Ranked for your volume

gpt-oss-120b monthly cost by provider

Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.

Input tokens per month (millions)Prompts, context and documents you send.Output tokens per month (millions)Tokens the model generates.

More requirements: caching, context, features, provider

Cached share of input (%)0 = no caching. Only documented cache-read rates qualify.Required context per request (tokens)0 = any. Providers without a sufficient known limit are excluded.Required featureProvider requirement

Cheapest provider for your volume

W&B Inference (CoreWeave)

19 options · most expensive $18.00, 6.9× this price

$2.60estimated / month

Provider	Estimated / month	Input / 1M	Output / 1M	Cached input / 1M	Context
1 W&B Inference (CoreWeave)Inference providerCheapestPricing page	$2.60	$0.03	$0.17	Not listed	131K
2 DeepInfraInference providerPricing page	$2.81	$0.037	$0.17	Not listed	131K
3 Novita AIInference providerPricing page	$4.00	$0.05	$0.25	Not listed	131K
4 SiliconFlowInference providerPricing page	$6.00	$0.05	$0.45	Not listed	131K
5 Google Cloud Vertex AICloud platformPricing page	$6.30	$0.09	$0.36	Not listed	131K
6 OVHcloud AI EndpointsCloud platformBilled in EUR: €0.08 input, €0.40 output per 1M tokens. USD at the ECB rate of Nov 6, 2026 (1.1165).Pricing page	$7.15	$0.0893	$0.4466	Not listed	131K
7 BasetenInference providerPricing page	$8.00	$0.10	$0.50	$0.10	128K
8 Fireworks AIInference providerPricing page	$10.50	$0.15	$0.60	$0.015	131K
9 Together AIInference providerPricing page	$10.50	$0.15	$0.60	Not listed	131K
10 Amazon BedrockCloud platformPricing page	$10.50	$0.15	$0.60	Not listed	128K

Order depends on listed price for your volume only. No provider pays for its position.

What this estimate leaves out

Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.

Share this comparison as a Markdown table

For a post, a doc or a forum answer. The source line links back here, so readers can check today's prices.

Markdown

| gpt-oss-120b provider | Input / 1M tokens | Output / 1M tokens | 30M in + 10M out per month |
|---|---:|---:|---:|
| W&B Inference (CoreWeave) | $0.03 | $0.17 | $2.60 |
| DeepInfra | $0.037 | $0.17 | $2.81 |
| Novita AI | $0.05 | $0.25 | $4.00 |
| SiliconFlow | $0.05 | $0.45 | $6.00 |
| Google Cloud Vertex AI | $0.09 | $0.36 | $6.30 |
| OVHcloud AI Endpoints | $0.0893 | $0.4466 | $7.15 |
| Baseten | $0.10 | $0.50 | $8.00 |
| Amazon Bedrock | $0.15 | $0.60 | $10.50 |
| Fireworks AI | $0.15 | $0.60 | $10.50 |
| Microsoft Azure AI Foundry | $0.15 | $0.60 | $10.50 |

Standard list prices as of Nov 7, 2026 (cheapest 10 of 19 providers). Source: [AISelect.online](https://aiselect.online/models/gpt-oss-120b)

Accuracy: GPQA Diamond (graduate-level science questions) measured by Epoch AI (CC BY 4.0) on openai/gpt-oss-120b_high, run Dec 11, 2025. The model is the same at every provider, though quantized deployments can score lower.

Price history

The cheapest price has not changed since tracking started on Sep 28, 2026: $0.065 per 1M tokens at W&B Inference (CoreWeave). All price changes

Switch to the cheapest provider

Switch to W&B Inference (CoreWeave)

Already using the OpenAI SDK? Change the base URL, key and model name.

Show the code

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.inference.wandb.ai/v1",
    api_key=os.environ["WANDB_API_KEY"],
)
response = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello"}],
)

Base URL from W&B Inference (CoreWeave)'s API docs, model name from the open pricing datasets. Check the model page in W&B Inference (CoreWeave)'s docs before you switch production traffic.

Compare gpt-oss-120b with another model

gpt-oss-120b vs Llama 4 Maverick 17B 128E Instruct FP8 gpt-oss-120b vs DeepSeek V4 Flash 0731

Or pick any model

Model A

Model B

Before you pick a provider

Context windows differ by provider, from 128K to 131K tokens. A cheaper host may not accept your longest prompts.

2 of 19 providers list a cached-input price. Repeated system prompts or documents can cost much less there than the standard input rate shown above.

Our take: Cheapest gpt-oss-120b API: Hosts Differ by 7.8x for the Same Model

Keep comparing

More OpenAI models

gpt-oss-20b, GPT-5, GPT-5 Mini, GPT-5 Nano, GPT-4.1, GPT-4.1 mini, GPT-4o, GPT-4o mini